CLASSIFICATION OF RICE DISEASE USING

MACHINE LEARNING WITH DIAGNOSTIC

SYSTEM
WOX 7001

CHOW KINN JOHN 17090931

Outline
Introduction

Research Problem

RQ & RO

Literature Review

Research Design

Method

Significant & Conclusion

References

2
 Introduction
Rice is the staple food for many countries in the world
especially the Asia region. There have been many
challenges faced by rice farmers such as climate change
and rice plant diseases.

In this research, we will be using several machine learning

models to find out which model provides the best results in
detection and classification. Models such as Support Vector
Machine(SVM), Decision Tree algorithm, and CNN model.

(Venu Vasantha et al., 2022, pp. 1899–1911) A proposed

diagnostic system was created to identify the severity of
infection on the chosen four disease of rice plants.

3
Research Problem Statement

The emerge of multiple rice plant diseases have always been the major issue for
farmers in paddy fields. Failure to identify infected crops results in mass destruction of
crops and major yield loss. The advancement of computer science and technology has
created machine learning methods in detection of rice leaf diseases. The classification
of rice leaf disease had been done for most type of diseases. However, the machine
learning techniques used only able to perform detection and prediction based on
disease. It has limitations to know exactly the stages of the infection towards rice leaf
diseases. Thus, there still exist the research gap to improve the approach towards
identifying the phase of infection of rice leaf diseases.

4
 Research Question
I. What are some effective methods for detecting rice plant
diseases?
II. Which are the suitable machine learning tools for classification of
rice leaf diseases?
III. How can the proposed diagnostic system measure the severity of
a rice plant disease?

Research Objectives
I. To identify the available machine learnings tools that can be used
to detect rice leaf disease.
II. Evaluate chosen machine learning techniques performance based
on the accuracy and precision.
III. Analyse the rice leaf diseases using the proposed methodology to
measure the infection intensity and generate a diagnosis report.
Literature Review
Quantitative approach , using Uses three machine learning Uses CNN classification model and
historical weather data to predict the classifiers, which were Logistic proposed a Infection Intensity
happenings of rice blast disease of Regression, KNN, Decision Tree. Estimation Module. Provided a
different regions in Korea Decision Tree obtained the best diagnosis report.
performance

(Chaudhary & kumar, 2022) and

(Bashir et al., 2019) (Sharma et al., 2022)

(Kim et al., 2017) (Ahmed et al., 2019) (Venu Vasantha et al., 2022)

Both research results obtained shown

Uses SVM for classification of three that CNN was their best classification
rice leaf disease images and provided model for the rice leaf disease
a cure suggestion after prediction. images.

6
 Shorten Comparison
Diagnostic Report
Articles Best Method
System

Long Short Term Memory

(Kim et al., 2017) Absent
Neural Network

(Prajapati et al., 2017) and (Bashir Present with cure

SVM
et al., 2019) suggestion only

(Ahmed et al., 2019) Decision Tree Absent

(Chaudhary & kumar, 2022)

CNN Absent
and (Sharma et al., 2022)

Present with current

(Venu Vasantha et al., 2022)
CNN disease phase and
estimation of infection

7
Research Design

8
Research Methodology
IMAGE DATASET
Images obtain from Rice-leaf-disease. (2022, March 7). Kaggle. https://www.kaggle.com/datasets/chandrug/riceleafdisease

I M A G E P R O C E SS I N G A N D S E G M E N TAT IO N
• Crop to specific size, remove noise and set white background using Tensorflow.
F E AT U R E E X T R A C T IO N
• Gray level co-occurrence matrix (GLCM) for SVM and Decision Tree approach
• Convolutional layer filters and pooling layer for CNN approach

C L A SS I F IC AT IO N M O D E L S
• Dataset splitting 80% (Training) and 20% (Testing)
• SVM, Decision Tree and CNN
E VA LUAT IO N
• Confusion matrix to generate accuracy, precision, TP rate, FP rate, Recall

D I A G N O S I S R E P O RT
• Apply appropriate filters to the classified image in RGB, HSV and Grey scale format.
• Calculate the pixels of the disease region.

9
Significant and
Conclusion

The main contributions in the research

are that rice farmers able to save cost
and time to identify and conduct the
accurate treatment towards rice plant
diseases.

Providing a diagnosis report which is

easy to understand for farmers.

10
 Reference
Ahmed, K., Shahidi, T. R., Irfanul Alam, S. M., & Momen, S. (2019). Rice Leaf Disease Detection Using Machine Learning Techniques. 2019 International Conference on Sustainable

Technologies for Industry 4.0 (STI). https://doi.org/10.1109/sti47673.2019.9068096

Alfred, R., Obit, J. H., Chin, C. P. Y., Haviluddin, H., & Lim, Y. (2021). Towards Paddy Rice Smart Farming: A Review on Big Data, Machine Learning, and Rice Production Tasks. IEEE

Access, 9, 50358–50380. https://doi.org/10.1109/access.2021.3069449

Anami, B. S., Malvade, N. N., & Palaiah, S. (2020). Deep learning approach for recognition and classification of yield affecting paddy crop stresses using field images. Artificial

Intelligence in Agriculture, 4, 12–20. https://doi.org/10.1016/j.aiia.2020.03.001

Bashir, K., Rehman, M., & Bari, M. (2019). Detection and Classification of Rice Diseases: An Automated Approach Using Textural Features. January 2019, 38(1), 239–250.

https://doi.org/10.22581/muet1982.1901.20

Chaudhary, S., & kumar, U. (2022). Analysis of Methods of Machine Learning Techniques for Detection and Classification of Brown Spot (Rice) Disease. Universal Journal of

Agricultural Research, 10(5), 464–473. https://doi.org/10.13189/ujar.2022.100502

Chen, S., Zhang, K., Zhao, Y., Sun, Y., Ban, W., Chen, Y., Zhuang, H., Zhang, X., Liu, J., & Yang, T. (2021). An Approach for Rice Bacterial Leaf Streak Disease Segmentation and

Disease Severity Estimation. Agriculture, 11(5), 420. https://doi.org/10.3390/agriculture11050420

D. Vydeki, S. R. (1970). Application of machine learning in detection of blast disease in South Indian rice crops. Journal of Phytology, 31–37. https://doi.org/10.25081/jp.2019.v11.5476

Home - IRRI Rice Knowledge Bank. (n.d.). http://www.knowledgebank.irri.org/

Jagan, K., Balasubramanian, M., & Palanivel, S. (2016). Detection and Recognition of Diseases from Paddy Plant Leaf Images. International Journal of Computer Applications, 144(12),

34–41. https://doi.org/10.5120/ijca2016910505

Kaggle: Your Home for Data Science. (n.d.). https://www.kaggle.com/vbookshelf/rice-leaf-diseases.

Kaundal, R., Kapoor, A. S., & Raghava, G. P. (2006). Machine learning techniques in disease forecasting: a case study on rice blast prediction. BMC Bioinformatics, 7(1). 11
https://doi.org/10.1186/1471-2105-7-485
 Reference
Kim, Y., Roh, J. H., & Kim, H. (2017). Early Forecasting of Rice Blast Disease Using Long Short-Term Memory Recurrent Neural Networks. Sustainability, 10(2), 34. https://doi.org/10.3390/su10010034

M N Abu Bakar, Abu Abdullah, N. Abdul Rahim, Haniza Yazid, S.N. Misman, & Maz Jamilah Masnan. (2018). Rice Leaf Blast Disease Detection Using Multi-Level Colour Image Thresholding. Journal of

Telecommunication, Electronic and Computer Engineering, 10, 1–6. https://journal.utem.edu.my/index.php/jtec/article/download/4036/2974

Narmadha, R. P., & Arulvadivu, G. (2017). Detection and measurement of paddy leaf disease symptoms using image processing. 2017 International Conference on Computer Communication and Informatics

(ICCCI). https://doi.org/10.1109/iccci.2017.8117730

Patel, B., & Sharaff, A. (2021). Rice Crop Disease Prediction Using Machine Learning Technique. International Journal of Agricultural and Environmental Information Systems, 12(4), 1–15.

https://doi.org/10.4018/ijaeis.20211001.oa5

Prajapati, H. B., Shah, J. P., & Dabhi, V. K. (2017). Detection and classification of rice plant diseases. Intelligent Decision Technologies, 11(3), 357–373. https://doi.org/10.3233/idt-170301

Rice-leaf-disease. (2022, March 7). Kaggle. https://www.kaggle.com/datasets/chandrug/riceleafdisease

Sharma, R., Singh, A., Kavita, Z. Jhanjhi, N., Masud, M., Sami Jaha, E., & Verma, S. (2022). Plant Disease Diagnosis and Image Classification Using Deep Learning. Computers, Materials &Amp; Continua,

71(2), 2125–2140. https://doi.org/10.32604/cmc.2022.020017

Shutterstock. (n.d.). Stock Images, Photos, Vectors, Video, and Music. https://www.shutterstock.com/

Tan, B. T., Fam, P. S., Firdaus, R. B. R., Tan, M. L., & Gunaratne, M. S. (2021). Impact of Climate Change on Rice Yield in Malaysia: A Panel Data Analysis. Agriculture, 11(6), 569.

https://doi.org/10.3390/agriculture11060569

Venu Vasantha, S., Samreen, S., & Lakshmi Aparna, Y. (2022). Rice Disease Diagnosis System (RDDS). Computers, Materials & Continua 2022, 73(1), 1895–1914.

https://doi.org/10.32604/cmc.2022.028504

Zamani, A. S., Anand, L., Rane, K. P., Prabhu, P., Buttar, A. M., Pallathadka, H., Raghuvanshi, A., & Dugbakie, B. N. (2022). Performance of Machine Learning and Image Processing in Plant Leaf Disease

Detection. Journal of Food Quality, 2022, 1–7. https://doi.org/10.1155/2022/1598796

12
Thank You

13